From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from verein.lst.de ([213.95.11.211]:55083 "EHLO newverein.lst.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933326AbcKWIg7 (ORCPT ); Wed, 23 Nov 2016 03:36:59 -0500 Date: Wed, 23 Nov 2016 09:36:57 +0100 From: Christoph Hellwig Subject: Re: an iomap-based direct I/O implementation V3 Message-ID: <20161123083657.GA16966@lst.de> References: <1479064054-10474-1-git-send-email-hch@lst.de> <20161122225243.GN31101@dastard> <20161123000204.GO31101@dastard> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: Sender: linux-xfs-owner@vger.kernel.org List-ID: List-Id: xfs To: Jens Axboe Cc: Dave Chinner , Christoph Hellwig , linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org On Tue, Nov 22, 2016 at 05:40:30PM -0700, Jens Axboe wrote: > That's going to be somewhat harder... The REQ_IDLE used to be > REQ_NOIDLE. bio_iov_iter_get_pages() is a single commit, so that's easy > enough. The poll bits are 3-4 patches, so not too bad either. I think we'll simply need a tree that has latest master merged into the block tree as a base. The only other option would be to cherry-pick bio_iov_iter_get_pages from the block tree into the XFS tree, and I'll resend the series so that it doesn't require the other block changes, those are fairly mechanical merges that could be carried in linux-next.